1. Project Overview & Quickstart (PaddlePaddle/PaddleOCR)
File: README.md
PaddleOCR converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) with industry-leading accuracy. With 70k+ Stars and trusted by top-tier projects like Dify, RAGFlow, and Cherry Studio, PaddleOCR is the bedrock for building intelligent RAG and Agentic applications.
🚀 Key Features
📄 Intelligent Document Parsing (LLM-Ready)
Transforming messy visuals into structured data for the LLM era.
- SOTA Document VLM: Featuring PaddleOCR-VL-1.6 (0.9B), the industry's leading lightweight vision-language model for document parsing. It achieves 96.3% accuracy on OmniDocBench v1.6, leads in text, formula, and table recognition, and shows significantly enhanced capabilities in ancient documents, rare characters, seals, and charts, with structured outputs in Markdown and JSON formats.
- Structure-Aware Conversion: Powered by PP-StructureV3, seamlessly convert complex PDFs and images into Markdown or JSON. Unlike the PaddleOCR-VL series models, it provides more fine-grained coordinate information, including table cell coordinates, text coordinates, and more.
- Production-Ready Efficiency: Achieve commercial-grade accuracy with an ultra-small footprint. Outperforms numerous closed-source solutions in public benchmarks while remaining resource-efficient for edge/cloud deployment.
🔍 Universal Text Recognition (Scene OCR)
The global gold standard for high-speed, multilingual text spotting.
- 100+ Languages Supported: Native recognition for a vast global library. PP-OCRv6 supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages) — no model switching needed for multilingual documents.
- Complex Element Mastery: Beyond standard text recognition, we support natural scene text spotting across a wide range of environments, including IDs, street views, books, and industrial components
- Performance Leap: PP-OCRv6 achieves +4.6% detection and +5.1% recognition accuracy over PP-OCRv5, surpassing mainstream Vision-Language Models. 5.2× CPU inference speedup end-to-end.
🛠️ Developer-Centric Ecosystem
- Seamless Integration: The premier choice for the AI Agent ecosystem—deeply integrated with Dify, RAGFlow, Pathway, and Cherry Studio.
- LLM Data Flywheel: A complete pipeline to build high-quality datasets, providing a sustainable "Data Engine" for fine-tuning Large Language Models.
- One-Click Deployment: Supports various hardware backends (NVIDIA GPU, Intel CPU, Kunlunxin XPU, and diverse AI Accelerators).
📣 Recent updates
🔥 2026.07.22: HPD-Parsing is now available
- HPD-Parsing is a lightweight vision-language model designed for high-throughput document parsing. It adopts a hierarchical parallel decoding paradigm and Progressive Multi-Token Prediction (P-MTP), achieving a peak throughput of 4,752 tokens/s on public benchmarks while maintaining competitive parsing accuracy.
- HPD-Parsing supports both OpenAI-compatible serving and local inference through a customized vLLM runtime, making it suitable for document parsing scenarios with high demands on inference efficiency and deployment throughput.
- See the HPD-Parsing usage tutorial for environment setup, serving, and local inference instructions.
2026.06.11: Release of PaddleOCR 3.7.0
PP-OCRv6 highlights:
- Accuracy boost: Medium tier achieves +4.6% detection and +5.1% recognition over PP-OCRv5_server, surpassing mainstream VLMs (Qwen3-VL-235B, GPT-5.5) with only 34.5M parameters.
- 50 languages unified: Single model covers Chinese, English, Japanese, and 46 Latin-script languages — no model switching needed.
- Specialized scenarios: Major improvements in digital displays, dot-matrix characters, tire prints, and industrial text recognition.
- Faster inference: 5.2× CPU speedup (OpenVINO), 6.1× on Apple M4 (tiny), 0.13s on A100 GPU.
- Three tiers for all scenarios: tiny (1.5M) / small (7.7M) / medium (34.5M) for edge, mobile, and server deployment.
- Model availability: All models are available on HuggingFace and ModelScope.
2026.05.28: Release of PaddleOCR 3.6.0
PaddleOCR-VL-1.6 highlights:
- New SOTA Accuracy: Achieves over 96.3% on OmniDocBench v1.6, also sets new SOTA on OmniDocBench v1.5 and Real5-OmniDocBench, leading both open-source and proprietary solutions in text, formula, and table recognition.
- Comprehensive Capability Upgrade: Significant improvements in table, ancient document, and rare character recognition, with notably enhanced seal recognition, spotting, and chart understanding across multiple scenarios.
- Seamless Migration: Model architecture is fully consistent with PaddleOCR-VL-1.5, enabling zero-cost adaptation—swap and go.
- Try it now: Available on HuggingFace or our Official Website.
2026.04.21: Release of PaddleOCR 3.5.0
- Flexible inference backends: Seamlessly switch between Paddle static graph, Paddle dynamic graph, or Transformers. PaddleOCR is now deeply integrated with the Hugging Face ecosystem, and 20 major models support Transformers as the inference backend.
- Office documents to Markdown: Convert common document formats such as Word, Excel, and PowerPoint into Markdown.
- DOCX export for parsed results: The
PaddleOCR-VLseries,PP-StructureV3, andPP-DocTranslationnow support exporting parsed results to DOCX for convenient viewing and editing in Microsoft Word. - Official browser inference SDK: Released
PaddleOCR.js, the official browser inference SDK that supports runningPP-OCRv5directly in the browser.
2026.01.29: Release of PaddleOCR 3.4.0
- PaddleOCR-VL-1.5 (SOTA 0.9B VLM): Our latest flagship model for document parsing is now live!
- 94.5% Accuracy on OmniDocBench: Surpassing top-tier general large models and specialized document parsers.
- Real-World Robustness: First to introduce the PP-DocLayoutV3 algorithm for irregular shape positioning, mastering 5 tough scenarios: Skew, Warping, Scanning, Illumination, and Screen Photography.
- Capability Expansion: Now supports Seal Recognition, Text Spotting, and expands to 111 languages (including China’s Tibetan script and Bengali).
- Long Document Mastery: Supports automatic cross-page table merging and hierarchical heading identification.
- Try it now: Available on HuggingFace or our Official Website.
2025.10.16: Release of PaddleOCR 3.3.0
Released PaddleOCR-VL:
Model Introduction:
- PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. The model has been released on HuggingFace. Everyone is welcome to download and use it! More introduction information can be found in PaddleOCR-VL.
Core Features:
- Compact yet Powerful VLM Architecture: We present a novel vision-language model that is specifically designed for resource-efficient inference, achieving outstanding performance in element recognition. By integrating a NaViT-style dynamic high-resolution visual encoder with the lightweight ERNIE-4.5-0.3B language model, we significantly enhance the model’s recognition capabilities and decoding efficiency. This integration maintains high accuracy while reducing computational demands, making it well-suited for efficient and practical document processing applications.
- SOTA Performance on Document Parsing: PaddleOCR-VL achieves state-of-the-art performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions and exhibiting strong competitiveness against leading vision-language models (VLMs) in document parsing. Moreover, it excels in recognizing complex document elements, such as text, tables, formulas, and charts, making it suitable for a wide range of challenging content types, including handwritten text and historical documents. This makes it highly versatile and suitable for a wide range of document types and scenarios.
- Multilingual Support: PaddleOCR-VL Supports 109 languages, covering major global languages, including but not limited to Chinese, English, Japanese, Latin, and Korean, as well as languages with different scripts and structures, such as Russian (Cyrillic script), Arabic, Hindi (Devanagari script), and Thai. This broad language coverage substantially enhances the applicability of our system to multilingual and globalized document processing scenarios.
Released PP-OCRv5 Multilingual Recognition Model:
- Improved the accuracy and coverage of Latin script recognition; added support for Cyrillic, Arabic, Devanagari, Telugu, Tamil, and other language systems, covering recognition of 109 languages. The model has only 2M parameters, and the accuracy of some models has increased by over 40% compared to the previous generation.
2025.08.21: Release of PaddleOCR 3.2.0
Significant Model Additions:
- Introduced training, inference, and deployment for PP-OCRv5 recognition models in English, Thai, and Greek. The PP-OCRv5 English model delivers an 11% improvement in English scenarios compared to the main PP-OCRv5 model, with the Thai and Greek recognition models achieving accuracies of 82.68% and 89.28%, respectively.
Deployment Capability Upgrades:
- Full support for PaddlePaddle framework versions 3.1.0 and 3.1.1.
- Comprehensive upgrade of the PP-OCRv5 C++ local deployment solution, now supporting both Linux and Windows, with feature parity and identical accuracy to the Python implementation.
- High-performance inference now supports CUDA 12, and inference can be performed using either the Paddle Inference or ONNX Runtime backends.
- The high-stability service-oriented deployment solution is now fully open-sourced, allowing users to customize Docker images and SDKs as required.
- The high-stability service-oriented deployment solution also supports invocation via manually constructed HTTP requests, enabling client-side code development in any programming language.
Benchmark Support:
- All production lines now support fine-grained benchmarking, enabling measurement of end-to-end inference time as well as per-layer and per-module latency data to assist with performance analysis. Here's how to set up and use the benchmark feature.
- Documentation has been updated to include key metrics for commonly used configurations on mainstream hardware, such as inference latency and memory usage, providing deployment references for users.
Bug Fixes:
- Resolved the issue of failed log saving during model training.
- Upgraded the data augmentation component for formula models for compatibility with newer versions of the albumentations dependency, and fixed deadlock warnings when using the tokenizers package in multi-process scenarios.
- Fixed inconsistencies in switch behaviors (e.g.,
use_chart_parsing) in the PP-StructureV3 configuration files compared to other pipelines.
Other Enhancements:
- Separated core and optional dependencies. Only minimal core dependencies are required for basic text recognition; additional dependencies for document parsing and information extraction can be installed as needed.
- Enabled support for NVIDIA RTX 50 series graphics cards on Windows; users can refer to the installation guide for the corresponding PaddlePaddle framework versions.
- PP-OCR series models now support returning single-character coordinates.
- Added AIStudio, ModelScope, and other model download sources, allowing users to specify the source for model downloads.
- Added support for chart-to-table conversion via the PP-Chart2Table module.
- Optimized documentation descriptions to improve usability.
🚀 Quick Start
Step 1: Try Online
PaddleOCR official website provides interactive Experience Center and APIs—no setup required, just one click to experience.
Step 2: Local Deployment
For local usage, please refer to the following documentation based on your needs:
- PP-OCR Series: See PP-OCR Documentation
- PaddleOCR-VL Series: See PaddleOCR-VL Documentation
- PP-StructureV3: See PP-StructureV3 Documentation
- More Capabilities: See More Capabilities Documentation
🧩 More Features
- Convert models to ONNX format: Obtaining ONNX Models.
- Accelerate inference using engines like OpenVINO, ONNX Runtime, TensorRT, or perform inference using ONNX format models: High-Performance Inference.
- Accelerate inference using multi-GPU and multi-process: Parallel Inference for Pipelines.
- Integrate PaddleOCR into applications written in C++, C#, Java, etc.: Serving.
🔄 Quick Overview of Execution Results
PP-OCRv5
PP-StructureV3
PaddleOCR-VL
✨ Stay Tuned
⭐ Star this repository to keep up with exciting updates and new releases, including powerful OCR and document parsing capabilities! ⭐
👩👩👧👦 Community
😃 Awesome Projects Leveraging PaddleOCR
PaddleOCR wouldn't be where it is today without its incredible community! 💗 A massive thank you to all our longtime partners, new collaborators, and everyone who's poured their passion into PaddleOCR — whether we've named you or not. Your support fuels our fire!
👩👩👧👦 Contributors
🌟 Star
📄 License
This project is released under the Apache 2.0 license.
🎓 Citation
/* Detailed source-code truncated for AI context efficiency. */File: docs/index.md
comments: true
hide:
- navigation
- toc
PaddleOCR自发布以来凭借学术前沿算法和产业落地实践，受到了产学研各方的喜爱，并被广泛应用于众多知名开源项目，例如：Umi-OCR、OmniParser、MinerU、RAGFlow等，已成为广大开发者心中的开源OCR领域的首选工具。2025年5月20日，飞桨团队发布PaddleOCR 3.0，全面适配飞桨框架3.0正式版，进一步提升文字识别精度，支持多文字类型识别和手写体识别，满足大模型应用对复杂文档高精度解析的旺盛需求，结合文心大模型4.5显著提升关键信息抽取精度，并新增对昆仑芯、昇腾等国产硬件的支持。
2026 年 1 月 29 日，PaddleOCR 开源了先进、高效的文档解析模型 PaddleOCR-VL-1.5。PaddleOCR-VL-1.5 是 PaddleOCR-VL 系列的全新迭代版本。在全面优化 1.0 版本核心能力的基础上，该模型在文档解析权威评测集 OmniDocBench v1.5 上斩获了 94.5% 的高精度，超越了全球的顶尖通用大模型及文档解析专用模型。PaddleOCR-VL-1.5 创新性地支持了文档元素的异形框定位，使得 PaddleOCR-VL-1.5 在扫描、倾斜、弯折、屏幕拍摄及复杂光照等真实落地场景中均表现卓越，实现了全面的 SOTA。此外，模型进一步集成了印章识别与文本检测识别任务，关键指标持续领跑主流模型。
2026 年 5 月 28 日，PaddleOCR 开源了 PaddleOCR-VL-1.6，作为 PaddleOCR-VL 系列的最新版本。 PaddleOCR-VL-1.6 以 96.3% 精度再次刷新评测集 OmniDocBench v1.6，并在 OmniDocBench v1.5、Real5-OmniDocBench 上同步达到全新 SOTA，文本、公式、表格识别全面领先开源与闭源方案。此外，模型在古籍、生僻字识别上大幅提升，印章、spotting、图表识别等多场景能力也显著增强。PaddleOCR-VL-1.6 在 PaddleOCR-VL-1.5 的基础上进一步升级了 VLM 组件（PaddleOCR-VL-1.6-0.9B），并继续采用 PP-DocLayoutV3 作为版面分析模型；模型结构与 PaddleOCR-VL-1.5 完全一致，支持零成本无缝迁移。
2026 年 6 月 11 日，PaddleOCR 发布 PP-OCRv6，作为 PP-OCR 系列的最新版本。 PP-OCRv6 基于全新设计的 PPLCNetV4 统一骨干网络，提供 tiny/small/medium 三档模型（1.5M~34.5M 参数）。在精度方面，medium 档相比 PP-OCRv5_server 识别精度提升 5.1%、检测精度提升 4.6%，以仅 34.5M 参数的规模超越 Qwen3-VL-235B、GPT-5.5 等大型视觉语言模型。在多语种方面，单一模型统一支持中文、英文、日文及 46 种拉丁语系共 50 种语言，无需为不同语种切换模型。在场景覆盖方面，PP-OCRv6 大幅提升了数码管、点阵字符、轮胎印字、工业字符等传统 VLM 难以覆盖的专业场景识别能力。在速度方面，PP-OCRv6_medium 在 Intel Xeon CPU OpenVINO 下相比 PP-OCRv5_server 加速 5.2×（1.40s vs 7.30s），tiny 档在纯前端浏览器环境的极低算力下，直接轰出了单图 97ms 的惊人成绩。
您可以在 PaddleOCR官网 在线使用或者调用该模型的API。
PaddleOCR 3.x 核心特色能力：
PaddleOCR-VL - 通过 0.9B 超紧凑视觉语言模型增强多语种文档解析
面向文档解析的 SOTA 且资源高效的模型, 支持 109 种语言，在复杂元素（如文本、表格、公式和图表）识别方面表现出色，同时资源消耗极低。PP-OCRv6 — 全场景多语言文字识别
单模型支持 50 种语言（中、英、日及 46 种拉丁语系），检测精度提升 4.6%、识别精度提升 5.1%，超越主流视觉语言大模型。medium 档位模型端到端 CPU 推理加速 5.2×，覆盖数码屏/点阵/工业字符等专业场景。三档模型（tiny/small/medium，1.5M~34.5M 参数）满足端侧到服务端全场景部署。PP-StructureV3 — 复杂文档解析
将复杂PDF和文档图像智能转换为保留原始结构的Markdown文件和JSON文件，在公开评测中领先众多商业方案。完美保持文档版式和层次结构。PP-ChatOCRv4 — 智能信息抽取
原生集成ERNIE 4.5，从海量文档中精准提取关键信息，精度较上一代提升15个百分点。让文档"听懂"您的问题并给出准确答案。
💡 Tips
PaddleOCR 官网免费 API 调用现已将每日文档解析上限提升至 20,000 页，支持大批量 PDF 文件解析，同时提供 MCP 及 Skills 服务。更多详情请参见 PaddleOCR 官网。
PaddleOCR 3.0 除了提供优秀的模型库外，还提供覆盖模型训练、推理和服务化部署等环节的易用工具，方便开发者快速落地 AI 应用。
此外，PaddleOCR 还提供官方 Agent Skills，便于在支持 Skills 的 AI 应用中调用文字识别、文档解析等能力。
您可直接快速开始，或查阅完整的 PaddleOCR 文档，或通过 Github Issues 获取支持，或在 AIStudio 课程平台 探索我们的 OCR 课程。
特别说明：PaddleOCR 3.x 引入了多项重要的接口变动，基于 PaddleOCR 2.x 编写的旧代码很可能无法使用 PaddleOCR 3.x 运行。请确保您阅读的文档与实际使用的 PaddleOCR 版本匹配。此文档 阐述了升级原因及 PaddleOCR 2.x 到 PaddleOCR 3.x 的主要变更。
🔄 快速一览运行效果
PP-OCRv5
PP-StructureV3
PaddleOCR-VL
👩👩👧👦 PaddleOCR OCEAN 生态联盟
单点技术的领先只是开始，生态的繁荣才是长期价值所在。为了让 OCR 及文档智能技术更好地服务于全球开发者和产业场景，我们正式发起 PaddleOCR OCEAN 生态联盟。
联盟名称 OCEAN 蕴含五大核心：
- Open Source – 开源为本
- Community – 社区驱动
- Ecosystem – 生态共赢
- Application – 应用落地
- Network – 网络互联
定位：以开源共建为核心的生态联盟，面向全球OCR及文档智能上下游伙伴，不涉及商业排他、不干预伙伴独立商业选择，聚焦技术共建、社区联动与影响力互换。以开放、共生、共赢为核心理念，汇聚开发者、平台方、应用方，共同推动 OCR 技术的全链条应用与生态繁荣。联盟致力于实现生态全链条应用规模与衍生项目数量的双重提升，让全球开发者与用户共享 OCR 技术发展的红利。
加入我们：与志同道合者，共赴深水区
PaddleOCR OCEAN生态联盟面向全球OCR及文档智能上下游伙伴开放。我们深知：生态的价值不在于数量，而在于质量。
我们期待这样的伙伴加入：
- 真心认同开源精神，愿意以开放的心态共建、共享
- 具备持续贡献的意愿与能力，无论是代码、场景案例还是平台集成
- 愿意与联盟共同成长，不追求短期流量，而是深耕长期价值
联盟不是荣誉墙，而是行动者的集结号。
我们将对每一份申请进行审慎评估，优先邀请那些已经在PaddleOCR生态中有所行动、或具备明确共建规划的伙伴。我们不追求“大而全”，而是希望与真正志同道合的机构和个人，在OCR深水区携手深耕。
如果您符合以上理念，欢迎通过以下方式与我们联系：
- 发送邮件至 [email protected]，简要介绍您与PaddleOCR的合作情况或共建计划
2. Official Technical Reference & Guides (PaddlePaddle/docs)
PaddlePaddle docs
Source files for contents presented at PaddlePaddle documentation.
Note: English version API docs are generally docstrings in PaddlePaddle/Paddle, documents for other PaddlePaddle projects are being managed in their respective ways.
Codebase structure
- docs: PaddlePaddle 2.0 & above docs source file.
- docs/api: PaddlePaddle API docs.
- docs/guides: PaddlePaddle guides docs.
- docs/tutorial: PaddlePaddle tutorial docs.
- ci_scripts: docs CI scripts.
How to build
- pre-requirements
- docker
- Instructions
- step1: clone docstext
git clone https://github.com/PaddlePaddle/docs - step2: build docstext
cd docs mkdir output bash docs-build.sh -f absolute_path_docs - step3: preview docs
The output of docs will be generated in docs/output.
- step1: clone docs
How to contribute
PaddlePaddle welcomes documentation contributions, please see CONTRIBUTING.md for details.